The current ubiquity of smart phones with mobile Internet and several short-range wireless interfaces (NFC, Bluetooth, Bluetooth Smart) and the fact that these devices are carried almost anytime and anywhere by users, enables potentially new pervasive sensing applications where smartphones can act as universal hubs for interaction with sensors (or sensor networks) that have only short-range wireless connectivity. Thus, in next years we can expect an increasing number of long-term and large-scale deployments for various crowd-sourced monitoring applications, such as environment monitoring, domestic utility meter reading, urban monitoring, etc. In this paper, we present the implementation and initial performance results with our mobile-cloud middleware that enables such opportunistic mobile sensing. One of the singular features of our middleware is the capability to discover, dynamically download and install sensor-specific transcoding modules on the mobile phone according to the encountered sensor type and make.
The majority of fatal car crashes are caused by reckless driving. With the sophistication of vehicle instrumentation, reckless maneuvers, such as abrupt turns, acceleration, and deceleration, can now be accurately detected by analyzing data related to the driver-vehicle interactions. Such analysis usually requires very specific in-vehicle hardware and infrastructure sensors (e.g. loop detectors and radars), which can be costly. Hence, in this paper, we investigated if off-the-shelf smartphones can be used to online detect and classify the driver's behavior in near real-time. To do so, we first modeled and performed an intrinsic evaluation to assess the performance of three outlier detection algorithms formulated as a data stream processing network which receives as input and processes data streams of smartphone and vehicle sensors. Next, we implemented a novel scoring mechanism based on online outlier detection to quantitatively evaluate drivers' maneuvers as either cautious or reckless. Thus, we adapted a data mining mechanism which takes into account a sensor's data rates and power to determine driver behavior in the scoring process. Finally, as the intrinsic evaluation does not necessarily reveal how well an algorithm will perform in a real-world scenario, we evaluated the algorithm that achieved the best result in a real-world case study to assess drivers' driving behavior. Our results indicate that the algorithm performs quickly and accurately; the algorithm classifies driver behavior with 95.45% accuracy. Moreover, such results are obtained within 100 milliseconds of processing time on average.
Current sharing-based applications combine new computing devices with smart spaces to provide content-level ubiquity, i.e., the possibility to exchange and move content freely in a ubiquitous environment. However, due to the environment complexity and lack of infrastructure platforms, most of the work in the area is repeatedly built from scratch using raw techniques, such as socket and rpc, to express content sharing. Aiming to provide an infrastructure for the development of this kind of applications, we propose Content Sharing for Smart Spaces (C3S), a middleware that offers a high-level programming model using primitives that are based on a set of content sharing semantics. They express a set of behaviors, move, clone, and mirror, which serve as a building blocks for developers to implement sharing and content ubiquity features.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.